Course Information

CS 754: Advanced image processing

Image transforms and statistics of natural images
survey of statistical properties of image transform coefficients
implications of     these statistics for important image processing applications such as     denoising, compression, source separation, deblurring and image forensics
non-local self-similarity in images

   (2) Dictionary learning and sparse representations in image processing
Overview of Principal Components Analysis (PCA), Singular Value Decomposition     (SVD) and Independent Components Analysis (ICA); PCA, SVD and ICA in the context of image processing
Sparse PCA
Concept of overcomplete dictionaries
Greedy pursuit algorithms: matching pursuit (MP), orthogonal matching pursuit (OMP)     and basis pursuit (BP)
Popular dictionary learning techniques: Method of Optimal Directions (MOD), Unions of Orthonormal Bases, K-SVD, Non-negative sparse coding – along with     applications in image compression, denoising, inpainting and deblurring
Sparsity-seeking algorithms: iterative shrinkage and thresholding (ISTA)
    (3) Compressed Sensing (CS)
Concept and need for     CS
Theoretical     treatment: concept of coherence, null-space property and restricted     isometry property, proof of a key theorem in CS
Algorithms for CS  (covered in part 2) and some key properties of these algorithms
Applications of CS:     Rice Single Pixel Camera and its variants, Video compressed sensing, Color and Hyperspectral CS, Applications in Magnetic Resonance Imaging (MRI), Implications for Computed Tomography
CS under Forward Model Perturbations: a few key results and their proofs as well as     applications
Designing Forward Models for CS
Low-rank matrix estimation and Robust Principal Components Analysis: concept and application scenarios in image processing, statement of some key theorems, and proof of one important theorem

We will extensively refer to the following textbooks, besides a number of research papers from journals such as IEEE Transactions on Image Processing, IEEE Transactions on Signal Processing, and IEEE Transactions on Pattern Analysis and Machine Intelligence:

"Natural Image Statistics"     by Aapo Hyvarinen, Jarmo Hurri and Patrick Hoyer, Springer Verlag     2009 (http://www.naturalimagestatistics.net/     - freely downloadable online)
"A Mathematical Introduction to Compressive Sensing" by Simon Foucart and Holger Rauhut, Birkhauser,2013 (http://www.springer.com/us/book/9780817649470     )
Home Page


CS 663 (Fundamentals of Digital Image Processing) or EE 610 (Image Processing) or CS 725 or CS 726 or Instructor Consent
Other Details

Duration : Full Semester Total Credit : 0
Type : Theory
Current Semester (Autumn 2017-18)

Status : Not Offered Instructor : ---
Next Semester (Spring 2017-18)

Status : Offered Instructor : Prof. Ajit Rajwade

Last Modified Date: 09-May-2016


Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback